Lists (14)
Starred repositories
The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling.
Practitioner-grade technical books bridging fragmented fields into unified, actionable knowledge.
Safe refund policy layer for AI agents — Python + TypeScript. Same behavior, shared tests.
a minimalist interactive scripting language with efficient blocking I/O and conditional replies. Built from scratch in C. Future: user‑defined blocks for self‑modifying syntax.
Window peeking, alt-tab and other enhancements for macOS
Context Minifier & State Guard — Local-first MCP middleware proxy
Measure AI coding tool impact with commit-level extraction, optional AI scoring, and productivity analysis for GitHub and GitLab codebases. Claude Code plugin.
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling.
Rust and Python library for the game of Connect4. ML/DL support.
Architecture, patterns & internals of Anthropic's AI coding agent — reverse-engineered from source maps
A from-scratch LLM inference engine that uses wgpu (the cross-platform WebGPU implementation) to dispatch WGSL compute shaders for every math operation a Transformer needs. No CUDA. No Python. No m…
A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Implementing from scratch "Where are they looking?" NeurIPS 2015
A CLI tool for managing and distributing agent skills across projects
A restful API designed to route user prompts to various AI model providers.
High-performance, cross-platform utility designed to redefine how you acquire and manage digital media.
Cross-node Claude Code session continuity via Syncthing
Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that kno…
An experience-driven self-improvement framework for LLM agents — 基于经验的 LLM Agent 自我改进框架
2
Updated Apr 11, 2026
A dungeon crawler that runs on top of your Ollama CLI. Every prompt goes deeper. Monsters, loot, and an Oracle who answers your questions in medieval English.
🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing.
MCP-first tectonochemical forecasting engine for reproducible hydrocarbon-nitrogen-water modeling and paper-ready artifacts.